Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5731 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.8382. Min Act: -0.1700
Data Index: 1095688 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.7132. Min Act: -0.1700
Data Index: 1873598 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.6819. Min Act: -0.1700
Data Index: 7962177 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.6194. Min Act: -0.1700
Data Index: 2283011 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.6507. Min Act: -0.1700
Data Index: 7390268 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.5882. Min Act: -0.1700
Data Index: 3817257 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.5569. Min Act: -0.1700
Data Index: 5002724 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.5569. Min Act: -0.1700
Data Index: 635821 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.5257. Min Act: -0.1700
Data Index: 3198581 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4944. Min Act: -0.1700
Data Index: 4160111 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4621110 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4944. Min Act: -0.1700
Data Index: 1525235 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4944. Min Act: -0.1700
Data Index: 2075818 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4704554 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4632. Min Act: -0.1700
Data Index: 180334 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4319. Min Act: -0.1700
Data Index: 4832994 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4319. Min Act: -0.1700
Data Index: 6299080 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2451190 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4007. Min Act: -0.1700
Data Index: 1518424 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8382. Min Range: -5.8382
Max Act: 5.4007. Min Act: -0.1700
Data Index: 503068 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19